developer_uid: realhusoyun
submission_id: cycy233-misllm-v6-2-2-5_v18
model_name: cycy233-misllm-v6-2-2-5_v18
model_group: cycy233/misllm_v6.2.2.5
status: torndown
timestamp: 2024-09-23T17:50:30+00:00
num_battles: 20206
num_wins: 9716
celo_rating: 1225.93
family_friendly_score: 0.0
submission_type: basic
model_repo: cycy233/misllm_v6.2.2.5
model_architecture: MistralForCausalLM
model_num_parameters: 7248023552.0
best_of: 8
max_input_tokens: 1024
max_output_tokens: 64
latencies: [{'batch_size': 1, 'throughput': 0.9024302277842378, 'latency_mean': 1.1080497419834137, 'latency_p50': 1.104071021080017, 'latency_p90': 1.2330515384674072}, {'batch_size': 4, 'throughput': 1.9551562183851336, 'latency_mean': 2.0371346569061277, 'latency_p50': 2.053030014038086, 'latency_p90': 2.2511966228485107}, {'batch_size': 5, 'throughput': 2.0894002207111506, 'latency_mean': 2.376979041099548, 'latency_p50': 2.391704797744751, 'latency_p90': 2.620859980583191}, {'batch_size': 8, 'throughput': 2.3351838453891633, 'latency_mean': 3.3974766063690187, 'latency_p50': 3.406305193901062, 'latency_p90': 3.836595582962036}, {'batch_size': 10, 'throughput': 2.363564132974691, 'latency_mean': 4.200144491195679, 'latency_p50': 4.222379803657532, 'latency_p90': 4.777683115005493}, {'batch_size': 12, 'throughput': 2.4016982062398404, 'latency_mean': 4.946184355020523, 'latency_p50': 4.931912302970886, 'latency_p90': 5.653247284889221}, {'batch_size': 15, 'throughput': 2.3957166616942773, 'latency_mean': 6.180861670970916, 'latency_p50': 6.1838618516922, 'latency_p90': 6.924712800979615}]
gpu_counts: {'NVIDIA RTX A5000': 1}
display_name: cycy233-misllm-v6-2-2-5_v18
is_internal_developer: False
language_model: cycy233/misllm_v6.2.2.5
model_size: 7B
ranking_group: single
throughput_3p7s: 2.37
us_pacific_date: 2024-09-23
win_ratio: 0.4808472730872018
generation_params: {'temperature': 1.0, 'top_p': 1.0, 'min_p': 0.0, 'top_k': 40, 'presence_penalty': 0.0, 'frequency_penalty': 0.0, 'stopping_words': ['\n'], 'max_input_tokens': 1024, 'best_of': 8, 'max_output_tokens': 64}
formatter: {'memory_template': "{bot_name}'s Persona: {memory}\n####\n", 'prompt_template': '{prompt}\n<START>\n', 'bot_template': '{bot_name}: {message}\n', 'user_template': '{user_name}: {message}\n', 'response_template': '{bot_name}:', 'truncate_by_message': False}
Resubmit model
Shutdown handler not registered because Python interpreter is not running in the main thread
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLizer
Starting job with name cycy233-misllm-v6-2-2-5-v18-mkmlizer
Waiting for job on cycy233-misllm-v6-2-2-5-v18-mkmlizer to finish
cycy233-misllm-v6-2-2-5-v18-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
cycy233-misllm-v6-2-2-5-v18-mkmlizer: ║     _____            __           __                                ║
cycy233-misllm-v6-2-2-5-v18-mkmlizer: ║    / _/ /_ ___    __/ /  ___ ___ / /                                ║
cycy233-misllm-v6-2-2-5-v18-mkmlizer: ║   / _/ / // / |/|/ / _ \/ -_) -_) /                                 ║
cycy233-misllm-v6-2-2-5-v18-mkmlizer: ║  /_//_/\_, /|__,__/_//_/\__/\__/_/                                  ║
cycy233-misllm-v6-2-2-5-v18-mkmlizer: ║       /___/                                                         ║
cycy233-misllm-v6-2-2-5-v18-mkmlizer: ║                                                                     ║
cycy233-misllm-v6-2-2-5-v18-mkmlizer: ║  Version: 0.10.1                                                    ║
cycy233-misllm-v6-2-2-5-v18-mkmlizer: ║  Copyright 2023 MK ONE TECHNOLOGIES Inc.                            ║
cycy233-misllm-v6-2-2-5-v18-mkmlizer: ║  https://mk1.ai                                                     ║
cycy233-misllm-v6-2-2-5-v18-mkmlizer: ║                                                                     ║
cycy233-misllm-v6-2-2-5-v18-mkmlizer: ║  The license key for the current software has been verified as      ║
cycy233-misllm-v6-2-2-5-v18-mkmlizer: ║  belonging to:                                                      ║
cycy233-misllm-v6-2-2-5-v18-mkmlizer: ║                                                                     ║
cycy233-misllm-v6-2-2-5-v18-mkmlizer: ║  Chai Research Corp.                                                ║
cycy233-misllm-v6-2-2-5-v18-mkmlizer: ║  Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f                   ║
cycy233-misllm-v6-2-2-5-v18-mkmlizer: ║  Expiration: 2024-10-15 23:59:59                                    ║
cycy233-misllm-v6-2-2-5-v18-mkmlizer: ║                                                                     ║
cycy233-misllm-v6-2-2-5-v18-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
cycy233-misllm-v6-2-2-5-v18-mkmlizer: Downloaded to shared memory in 20.968s
cycy233-misllm-v6-2-2-5-v18-mkmlizer: quantizing model to /dev/shm/model_cache, profile:s0, folder:/tmp/tmp_00b2q92, device:0
cycy233-misllm-v6-2-2-5-v18-mkmlizer: Saving flywheel model at /dev/shm/model_cache
cycy233-misllm-v6-2-2-5-v18-mkmlizer: quantized model in 17.424s
cycy233-misllm-v6-2-2-5-v18-mkmlizer: Processed model cycy233/misllm_v6.2.2.5 in 38.393s
cycy233-misllm-v6-2-2-5-v18-mkmlizer: creating bucket guanaco-mkml-models
cycy233-misllm-v6-2-2-5-v18-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
cycy233-misllm-v6-2-2-5-v18-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/cycy233-misllm-v6-2-2-5-v18
cycy233-misllm-v6-2-2-5-v18-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/cycy233-misllm-v6-2-2-5-v18/config.json
cycy233-misllm-v6-2-2-5-v18-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/cycy233-misllm-v6-2-2-5-v18/special_tokens_map.json
cycy233-misllm-v6-2-2-5-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/cycy233-misllm-v6-2-2-5-v18/tokenizer_config.json
cycy233-misllm-v6-2-2-5-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/cycy233-misllm-v6-2-2-5-v18/tokenizer.model
cycy233-misllm-v6-2-2-5-v18-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/cycy233-misllm-v6-2-2-5-v18/tokenizer.json
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Job cycy233-misllm-v6-2-2-5-v18-mkmlizer completed after 63.67s with status: succeeded
Stopping job with name cycy233-misllm-v6-2-2-5-v18-mkmlizer
Pipeline stage MKMLizer completed in 64.70s
run pipeline stage %s
Running pipeline stage MKMLTemplater
Pipeline stage MKMLTemplater completed in 0.17s
run pipeline stage %s
Running pipeline stage MKMLDeployer
Creating inference service cycy233-misllm-v6-2-2-5-v18
Waiting for inference service cycy233-misllm-v6-2-2-5-v18 to be ready
Failed to get response for submission zonemercy-vingt-deux-v0-1e5_v19: ('http://zonemercy-vingt-deux-v0-1e5-v19-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:50102->127.0.0.1:8080: read: connection reset by peer\n')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Failed to get response for submission zonemercy-vingt-deux-v0-1e5_v16: ('http://zonemercy-vingt-deux-v0-1e5-v16-predictor.tenant-chaiml-guanaco.k.chaiverse.com/v1/models/GPT-J-6B-lit-v2:predict', 'read tcp 127.0.0.1:40904->127.0.0.1:8080: read: connection reset by peer\n')
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Inference service cycy233-misllm-v6-2-2-5-v18 ready after 191.70063018798828s
Pipeline stage MKMLDeployer completed in 192.19s
run pipeline stage %s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.2718257904052734s
Received healthy response to inference request in 3.249235153198242s
Received healthy response to inference request in 1.30985426902771s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Connection pool is full, discarding connection: %s. Connection pool size: %s
Received healthy response to inference request in 1.315927267074585s
Received healthy response to inference request in 1.273684024810791s
5 requests
0 failed requests
5th percentile: 1.2809180736541748
10th percentile: 1.2881521224975585
20th percentile: 1.3026202201843262
30th percentile: 1.311068868637085
40th percentile: 1.313498067855835
50th percentile: 1.315927267074585
60th percentile: 1.6982866764068603
70th percentile: 2.0806460857391356
80th percentile: 2.4673076629638673
90th percentile: 2.858271408081055
95th percentile: 3.0537532806396483
99th percentile: 3.2101387786865234
mean time: 1.8841053009033204
Pipeline stage StressChecker completed in 10.39s
run pipeline stage %s
Running pipeline stage TriggerMKMLProfilingPipeline
run_pipeline:run_in_cloud %s
starting trigger_guanaco_pipeline args=%s
Pipeline stage TriggerMKMLProfilingPipeline completed in 7.37s
Shutdown handler de-registered
cycy233-misllm-v6-2-2-5_v18 status is now deployed due to DeploymentManager action
Shutdown handler registered
run pipeline %s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Skipping teardown as no inference service was successfully deployed
Pipeline stage MKMLProfilerDeleter completed in 0.12s
run pipeline stage %s
Running pipeline stage MKMLProfilerTemplater
Pipeline stage MKMLProfilerTemplater completed in 0.13s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeployer
Creating inference service cycy233-misllm-v6-2-2-5-v18-profiler
Waiting for inference service cycy233-misllm-v6-2-2-5-v18-profiler to be ready
Inference service cycy233-misllm-v6-2-2-5-v18-profiler ready after 190.50579285621643s
Pipeline stage MKMLProfilerDeployer completed in 190.87s
run pipeline stage %s
Running pipeline stage MKMLProfilerRunner
kubectl cp /code/guanaco/guanaco_inference_services/src/inference_scripts tenant-chaiml-guanaco/cycy233-misllm-v6-2-2-5-v18-profiler-predictor-00001-deploh2qqv:/code/chaiverse_profiler_1727114343 --namespace tenant-chaiml-guanaco
kubectl exec -it cycy233-misllm-v6-2-2-5-v18-profiler-predictor-00001-deploh2qqv --namespace tenant-chaiml-guanaco -- sh -c 'cd /code/chaiverse_profiler_1727114343 && python profiles.py profile --best_of_n 8 --auto_batch 5 --batches 1,5,10,15,20,25,30,35,40,45,50,55,60,65,70,75,80,85,90,95,100,105,110,115,120,125,130,135,140,145,150,155,160,165,170,175,180,185,190,195 --samples 200 --input_tokens 1024 --output_tokens 64 --summary /code/chaiverse_profiler_1727114343/summary.json'
kubectl exec -it cycy233-misllm-v6-2-2-5-v18-profiler-predictor-00001-deploh2qqv --namespace tenant-chaiml-guanaco -- bash -c 'cat /code/chaiverse_profiler_1727114343/summary.json'
Pipeline stage MKMLProfilerRunner completed in 761.23s
run pipeline stage %s
Running pipeline stage MKMLProfilerDeleter
Checking if service cycy233-misllm-v6-2-2-5-v18-profiler is running
Tearing down inference service cycy233-misllm-v6-2-2-5-v18-profiler
Service cycy233-misllm-v6-2-2-5-v18-profiler has been torndown
Pipeline stage MKMLProfilerDeleter completed in 2.18s
Shutdown handler de-registered
cycy233-misllm-v6-2-2-5_v18 status is now inactive due to auto deactivation removed underperforming models
cycy233-misllm-v6-2-2-5_v18 status is now torndown due to DeploymentManager action